CounterSketch: Physics-Grounded Counterfactual Reasoning for Sketch-to-Video Generation
cs.CV
Submitted: 2026-11-03
Updated: 2026-11-03
Terminology
Sources
- CoPhy: Counterfactual Learning of Physical Dynamics
- CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models
- What-If World: A Causal Benchmark for General World Models in Embodied Scenarios
- On the Surprising Robustness of Sequential Convex Optimization for Contact-Implicit Motion Planning
- Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
- PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance
- VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs